© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14402
    Prev
    Next
    INDEX
    Explanations

    unity game engine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    会
    -2.38
    ll
    -2.34
    其妙
    -2.30
     \"
    -2.20
    щита
    -2.19
     Grundstück
    -2.14
    Of
    -2.13
    已经
    -2.11
    各样的
    -2.11
     größte
    -2.09
    POSITIVE LOGITS
    ا
    2.38
    replyreport
    2.36
    使った
    2.30
     bús
    2.22
     guardado
    2.17
     alin
    2.13
    when
    2.08
    }$,
    2.06
    ”),
    2.05
     consumi
    2.03
    Activations Density 0.002%

    No Known Activations